© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 12091
    Prev
    Next
    INDEX
    Explanations

    mentions of specific ideas or concepts stated with emphasis or certainty

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    562
    +0.12
    0.5%
    393
    +0.11
    0.5%
    159
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    521
    +0.12
    0.03
    562
    +0.11
    0.03
    662
    +0.10
    0.03
    Negative Logits
    izont
    -0.78
    ãĥ³ãĤ¸
    -0.76
    izens
    -0.75
    greg
    -0.74
    sts
    -0.69
    ãĥ¼ãĥĨ
    -0.69
    ãĥ¯ãĥ³
    -0.69
    ulner
    -0.69
    imaru
    -0.68
    apolis
    -0.67
    POSITIVE LOGITS
     happens
    1.37
     happened
    1.21
     occurs
    1.15
     translates
    1.04
     happen
    1.00
     proves
    0.94
     occurred
    0.94
     applies
    0.91
     coincides
    0.90
     settles
    0.90
    Activations Density 0.069%

    No Known Activations